© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4871
    Prev
    Next
    INDEX
    Explanations

    phrases related to balance and equilibrium in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to equilibrium, balance, or fairness across different contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    concepts related to balance or equilibrium across systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thousand
    -0.41
     onItemClick
    -0.39
     discovery
    -0.37
    ->
    -0.37
    fireEvent
    -0.36
     congrès
    -0.36
     מוכ
    -0.35
    ‣
    -0.35
     Kunst
    -0.34
    Kunst
    -0.34
    POSITIVE LOGITS
     balance
    1.44
    balance
    1.40
     Balance
    1.39
     BALANCE
    1.32
    Balance
    1.31
     balancing
    1.23
     balances
    1.22
     Balancing
    1.15
    balancing
    1.14
    Balancing
    1.14
    Activations Density 0.147%

    No Known Activations